利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

23 条记录 (耗时 0.043 秒)

    Detection of 3-D videos
    11.
    发明授权
    Detection of 3-D videos 有权
    检测3-D视频

    公开(公告)号：US09106894B1

    公开(公告)日：2015-08-11

    申请号：US13367683

    申请日：2012-02-07

    申请人： Samuel Kvaalen ,  Jonathan Huang ,  Peter Bradshaw

    发明人： Samuel Kvaalen ,  Jonathan Huang ,  Peter Bradshaw

    IPC分类号： H04N13/00 ,  H04N7/12

    CPC分类号： G06F17/30153 ,  G06F17/30106 ,  G06F17/30784 ,  H04N13/161 ,  H04N13/271 ,  H04N13/275 ,  H04N13/324 ,  H04N13/344 ,  H04N19/597 ,  H04N2213/003

    摘要： Methods and systems related to the detection of 3-D video content are disclosed herein. Specifically, a video image file may be analyzed in order to determine if it contains 3-D stereoscopic video content. An assumption is made regarding the possible 3-D format of the video image file. The assumption could be that the video frame includes a left portion and a right portion where each portion contains respective stereoscopic image perspectives. Image analysis algorithms could be used to determine if the left and right portions are sufficiently similar to confirm the assumption. If so, an indication could be carried out that could include a change to metadata or a similar change to associated video image file information. If the left and right portions of the video frame are not sufficiently similar, another analysis may be performed to test a different 3-D file format assumption.

    摘要翻译： 本文公开了与检测3-D视频内容相关的方法和系统。 具体地，可以分析视频图像文件以便确定它是否包含3D立体视频内容。 假设视频图像文件的可能的3-D格式。 假设视频帧包括左部分和右部分，其中每个部分包含相应的立体图像透视图。 图像分析算法可用于确定左右部分是否足够相似以证实该假设。 如果是这样，可以执行可以包括对元数据的改变或对相关视频图像文件信息的类似改变的指示。 如果视频帧的左右部分不够相似，则可以执行另一分析来测试不同的3-D文件格式假定。

    High Performance AVC Encoder on a Multi-Core Platform
    12.
    发明申请
    High Performance AVC Encoder on a Multi-Core Platform 有权
    高性能AVC编码器在多核平台上

    公开(公告)号：US20120230391A1

    公开(公告)日：2012-09-13

    申请号：US13045436

    申请日：2011-03-10

    申请人： Jonathan Huang ,  Tsaifa Yu

    发明人： Jonathan Huang ,  Tsaifa Yu

    IPC分类号： H04N7/26

    CPC分类号： H04N19/436 ,  H04N19/177 ,  H04N19/503

    摘要： A method and system for encoding a digital video signal using a plurality of parallel processors. A digital picture is received that is composed of one or more GOPs. The CPU then determines the number of GOPs that need to be encoded and divides them into groups. The number of GOPs in a group may equal the number of parallel processors in the multi-core platform available to encode. The CPU transfers in a single batch to the multi-core platform, a frame of equal rank from each GOP contained in the first group. The multi-core platform encodes the frames in parallel, rearranges the encoded byte stream chunk into normal display order sequence and stores the encoded byte stream. The process may repeat until all the GOPs in the first group have been encoded. Upon completion the multi-core platform outputs the encoded byte stream in normal display order sequence.

    摘要翻译： 一种使用多个并行处理器对数字视频信号进行编码的方法和系统。 接收由一个或多个GOP组成的数字图像。 CPU然后确定需要编码的GOP的数量，并将它们分组。 组中的GOP的数量可以等于可用于编码的多核平台中的并行处理器的数量。 CPU将单批次传输到多核平台，这是与第一组中包含的每个GOP相等等级的一帧。 多核平台并行编码帧，将编码字节流块重新排列成正常显示顺序，并存储编码字节流。 该过程可以重复，直到第一组中的所有GOP已被编码。 完成后，多核平台以正常显示顺序序列输出编码字节流。

    High performance AVC encoder on a multi-core platform
    14.
    发明授权
    High performance AVC encoder on a multi-core platform 有权
    高性能AVC编码器在多核平台上

    公开(公告)号：US09148669B2

    公开(公告)日：2015-09-29

    申请号：US13045436

    申请日：2011-03-10

    申请人： Jonathan Huang ,  Tsaifa Yu

    发明人： Jonathan Huang ,  Tsaifa Yu

    IPC分类号： H04N7/12 ,  H04N19/436 ,  H04N19/503 ,  H04N19/177

    CPC分类号： H04N19/436 ,  H04N19/177 ,  H04N19/503

    摘要： A method and system for encoding a digital video signal using a plurality of parallel processors. A digital picture is received that is composed of one or more GOPs. The CPU then determines the number of GOPs that need to be encoded and divides them into groups. The number of GOPs in a group may equal the number of parallel processors in the multi-core platform available to encode. The CPU transfers in a single batch to the multi-core platform, a frame of equal rank from each GOP contained in the first group. The multi-core platform encodes the frames in parallel, rearranges the encoded byte stream chunk into normal display order sequence and stores the encoded byte stream. The process may repeat until all the GOPs in the first group have been encoded. Upon completion the multi-core platform outputs the encoded byte stream in normal display order sequence.

    摘要翻译： 一种使用多个并行处理器对数字视频信号进行编码的方法和系统。 接收由一个或多个GOP组成的数字图像。 CPU然后确定需要编码的GOP的数量，并将它们分组。 组中的GOP的数量可以等于可用于编码的多核平台中的并行处理器的数量。 CPU将单批次传输到多核平台，这是与第一组中包含的每个GOP相等等级的一帧。 多核平台并行编码帧，将编码字节流块重新排列成正常显示顺序，并存储编码字节流。 该过程可以重复，直到第一组中的所有GOP已被编码。 完成后，多核平台以正常显示顺序序列输出编码字节流。

    Systems and methods for 2D-to-3D conversion
    15.
    发明授权
    Systems and methods for 2D-to-3D conversion 有权
    2D到3D转换的系统和方法

    公开(公告)号：US08982185B1

    公开(公告)日：2015-03-17

    申请号：US13408960

    申请日：2012-02-29

    申请人： Vijnan Shastri ,  Jonathan Huang ,  Sam Kvaalen ,  Debargha Mukherjee ,  Chen Wu

    发明人： Vijnan Shastri ,  Jonathan Huang ,  Sam Kvaalen ,  Debargha Mukherjee ,  Chen Wu

    IPC分类号： H04N13/00 ,  H04N15/00

    CPC分类号： H04N13/139 ,  H04N13/167 ,  H04N13/356 ,  H04N21/23418 ,  H04N21/2343 ,  H04N21/816 ,  H04N21/854

    摘要： Systems and methods can facilitate identifying 2D content in media that is suitable for conversion into 3D content, and converting the suitable 2D content into 3D content. The identifying can be based on quality criteria applied to the 2D content. For 2D content converted into 3D content, a user can be offered a choice between viewing the content in its original 2D form, or viewing the content in its converted, 3D form. The systems and methods can thereby provide users with greater choice of content and an enhanced viewing experience.

    摘要翻译： 系统和方法可以促进识别适合于转换成3D内容的媒体中的2D内容，以及将合适的2D内容转换为3D内容。 识别可以基于应用于2D内容的质量标准。 对于转换为3D内容的2D内容，可以向用户提供以其原始2D形式查看内容或以其转换的3D形式查看内容的选择。 因此，系统和方法可以为用户提供更多的内容选择和增强的观看体验。

    Method and System for Automatic 3-D Image Creation
    16.
    发明申请
    Method and System for Automatic 3-D Image Creation 有权
    自动三维图像创建的方法和系统

    公开(公告)号：US20130201301A1

    公开(公告)日：2013-08-08

    申请号：US13601845

    申请日：2012-08-31

    申请人： Jonathan Huang ,  Samuel Kvaalen ,  Peter Bradshaw

    发明人： Jonathan Huang ,  Samuel Kvaalen ,  Peter Bradshaw

    IPC分类号： H04N13/02

    CPC分类号： H04N13/20 ,  G03B35/02 ,  G06K9/00 ,  G06K9/6215 ,  G06K9/66 ,  G06T7/00 ,  G06T7/285 ,  G06T7/593 ,  G06T7/70 ,  G06T15/205 ,  G06T2200/24 ,  G06T2207/20092 ,  G06T2207/20221 ,  G06T2207/30244 ,  H04N13/156 ,  H04N13/221 ,  H04N2213/003

    摘要： Disclosed herein are methods, devices, and non-transitory computer readable media that relate to stereoscopic image creation. A camera captures an initial image at an initial position. A target displacement from the initial position is determined for a desired stereoscopic effect, and an instruction is provided that specifies a direction in which to move the camera from the initial position. While the camera is in motion, an estimated displacement from the initial position is calculated. When the estimated displacement corresponds to the target displacement, the camera automatically captures a candidate image. An acceptability analysis is performed to determine whether the candidate image has acceptable image quality and acceptable similarity to the initial image. If the candidate image passes the acceptability analysis, a stereoscopic image is created based on the initial and candidate images.

    摘要翻译： 本文公开了与立体图像创建相关的方法，设备和非暂时性计算机可读介质。 相机在初始位置拍摄初始图像。 对于期望的立体效果确定从初始位置的目标位移，并且提供指定从初始位置移动相机的方向的指令。 当相机运动时，计算从初始位置的估计位移。 当估计的位移对应于目标位移时，相机自动捕获候选图像。 执行可接受性分析以确定候选图像是否具有可接受的图像质量和与初始图像的可接受的相似性。 如果候选图像通过可接受性分析，则基于初始和候选图像创建立体图像。

    Systems and methods for facilitating identification of and interaction with objects in a video or image frame
    17.
    发明授权
    Systems and methods for facilitating identification of and interaction with objects in a video or image frame 有权
    用于促进视频或图像帧中的对象的识别和交互的系统和方法

    公开(公告)号：US08837819B1

    公开(公告)日：2014-09-16

    申请号：US13440901

    申请日：2012-04-05

    申请人： Jennie Lees ,  Jonathan Huang

    发明人： Jennie Lees ,  Jonathan Huang

    IPC分类号： G06K9/00

    CPC分类号： G06K9/00718 ,  G06K9/34 ,  G06K9/6277

    摘要： Systems and methods for facilitating identification of and interaction with objects in a video frame are provided. In some embodiments, a system can include a computer-readable storage medium encoding computer executable components, and a processor that executes computer executable components encoded within the computer-readable storage medium. The components can include: a communication component that receives a video; a segmentation component that obtains a frame from the video; and a selection component that determines an object selected within the frame. The selection component can include a classifier trained using a probability map stored in the memory. The probability map can include information indicative of a likelihood that a pixel in the frame corresponds to the object, and can be generated based on crowdsourcing object differentiation.

    摘要翻译： 提供了用于促进视频帧中的对象的识别和交互的系统和方法。 在一些实施例中，系统可以包括编码计算机可执行组件的计算机可读存储介质和执行在计算机可读存储介质内编码的计算机可执行组件的处理器。 组件可以包括：接收视频的通信组件; 从视频获取帧的分割部件; 以及确定在该帧内选择的对象的选择组件。 选择组件可以包括使用存储在存储器中的概率图训练的分类器。 概率图可以包括指示帧中的像素对应于对象的可能性的信息，并且可以基于众包对象区分来生成。

    Method and system for automatic 3-D image creation
    18.
    发明授权
    Method and system for automatic 3-D image creation 有权
    自动三维图像创建的方法和系统

    公开(公告)号：US08259161B1

    公开(公告)日：2012-09-04

    申请号：US13366709

    申请日：2012-02-06

    申请人： Jonathan Huang ,  Samuel Kvaalen ,  Peter Bradshaw

    发明人： Jonathan Huang ,  Samuel Kvaalen ,  Peter Bradshaw

    IPC分类号： H04N13/02 ,  G06K9/00

    CPC分类号： H04N13/20 ,  G03B35/02 ,  G06K9/00 ,  G06K9/6215 ,  G06K9/66 ,  G06T7/00 ,  G06T7/285 ,  G06T7/593 ,  G06T7/70 ,  G06T15/205 ,  G06T2200/24 ,  G06T2207/20092 ,  G06T2207/20221 ,  G06T2207/30244 ,  H04N13/156 ,  H04N13/221 ,  H04N2213/003

    摘要： Disclosed herein are methods, devices, and non-transitory computer readable media that relate to stereoscopic image creation. A camera captures an initial image at an initial position. A target displacement from the initial position is determined for a desired stereoscopic effect, and an instruction is provided that specifies a direction in which to move the camera from the initial position. While the camera is in motion, an estimated displacement from the initial position is calculated. When the estimated displacement corresponds to the target displacement, the camera automatically captures a candidate image. An acceptability analysis is performed to determine whether the candidate image has acceptable image quality and acceptable similarity to the initial image. If the candidate image passes the acceptability analysis, a stereoscopic image is created based on the initial and candidate images.

    摘要翻译： 本文公开了与立体图像创建相关的方法，设备和非暂时性计算机可读介质。 相机在初始位置拍摄初始图像。 对于期望的立体效果确定从初始位置的目标位移，并且提供指定从初始位置移动相机的方向的指令。 当相机运动时，计算从初始位置的估计位移。 当估计的位移对应于目标位移时，相机自动捕获候选图像。 执行可接受性分析以确定候选图像是否具有可接受的图像质量和与初始图像的可接受的相似性。 如果候选图像通过可接受性分析，则基于初始和候选图像创建立体图像。

    Streaming-time 3D metadata injection
    19.
    发明授权
    Streaming-time 3D metadata injection 有权
    流媒体3D元数据注入

    公开(公告)号：US09420258B1

    公开(公告)日：2016-08-16

    申请号：US13367169

    申请日：2012-02-06

    申请人： Jonathan Huang ,  Andrew D. Berkheimer ,  Peter Bradshaw ,  Ben Hayden

    发明人： Jonathan Huang ,  Andrew D. Berkheimer ,  Peter Bradshaw ,  Ben Hayden

    IPC分类号： H04N13/00

    CPC分类号： H04N13/161 ,  H04N13/194

    摘要： Injection of 3D metadata into a requested video is disclosed. An input video and associated metadata are received by a video hosting site. If the metadata indicates that the input video is a 3D video, the 3D video system extracts the accompanying 3D metadata and stores it in an intermediate format, which is independent of the 3D metadata format and video format of the input video. The 3D video system stores the received video in a standard 2D video format in a video database. Responsive to a video streaming request of the input video, the 3D video system determines the actual 3D metadata format based on the video format of the requested video, and injects a modified 3D metadata associated with the input video into the requested video.

    摘要翻译： 公开了将3D元数据注入所请求的视频。 输入视频和相关联的元数据由视频托管站点接收。 如果元数据指示输入视频是3D视频，则3D视频系统提取伴随的3D元数据并将其存储为独立于输入视频的3D元数据格式和视频格式的中间格式。 3D视频系统将所接收的视频以标准2D视频格式存储在视频数据库中。 响应于输入视频的视频流请求，3D视频系统基于所请求的视频的视频格式确定实际的3D元数据格式，并将与输入视频相关联的修改的3D元数据注入到所请求的视频中。